Nodes/IAMCCS-nodes/MiniMax H3 Shotboard Settings → CineLinX
ComfyUI Node

MiniMax H3 Shotboard Settings → CineLinX

All the MiniMax H3 Shotboard settings, exported as one CineLinX config

By IAMCCS·Created 11 months ago·Updated 4 days ago· 113
MiniMax H3 Shotboard Settings → CineLinX
    • cine_linx
    duration_seconds10.00
    frame_rate24
    guide_policyevery_checked_row
    min_guide_gap_seconds0.00
    max_guides50
    default_force1.00
    promptrelay_epsilon0.0010
    ltx_round_modenone
    width960
    height544
    image_width960
    image_height544
    image_resize_methodcrop
    image_multiple_of32
    img_compression0
    task_modeauto_from_timeline
    audio_modeh3_native_generated
    prompt_mappingglobal_plus_local
    performance_profilelow_vram_balanced
    text_encoder_devicegpu_auto
    seed42
    seed_control_after_generate_compatfixed
    seed_stride1
    steps16
    sampler_nameeuler
    schedulersimple
    denoise1.00
    shift_video12.00
    shift_audio3.00
    turbo_modeoff
    turbo_lora_name
    turbo_strength1.00
    turbo_sampler_modeaudio_fixed
    reference_resize_policyoff
    reference_resize_megapixels0.50
    reference_resize_filterarea
    accelerationlow_vram_auto
    ref_image_sizematch
    sol_conditioningexact_kv_and_rows
    spectrum_profilelow_vram
    vram_clean_before_decodetrue
    rife_modeoff
    reference_role_1subject_identity
    reference_role_2subject_identity
    reference_role_3composition
    reference_role_4style
    reference_video_roleoff
    reference_audio_roleoff
    voice_reference_picture_index0
    v2v_guide_moderaw_only
    v2v_source_range_policytimeline_segment
    v2v_source_offset_seconds0.00
    v2v_source_fitcanvas_pad
    v2v_source_end_policyhold_last_for_grid
    v2v_audio_pairingpair_with_source_video
    flf_join_modeh3_keyframe_cut
    flf_overlap_frames9
    flf_continuity_modestable_keyframes
    flf_continuity_tail_frames22
    flf_continuity_audiotrue
    upscale_modeoff
    upscale_enabledfalse
    upscale_width1920
    upscale_height1080
    upscale_prompt
    upscale_sagetrue
    upscale_seed_offset10000
    wan_upscale_denoise0.20
    ltx_seam_safetrue
    ltx_detailer_enabledfalse
    ltx_detailer_lora_name
    ltx_detailer_strength0.60
    ltx_4k_enabledfalse
    ltx_4k_qualityULTRA
    ltx_looper_temporal_tile_size80
    ltx_looper_temporal_overlap24
    ltx_looper_guiding_strength1.00
    ltx_looper_overlap_strength0.50
    ltx_looper_cond_image_strength1.00
    ltx_looper_horizontal_tiles1
    ltx_looper_vertical_tiles1
    ltx_looper_spatial_overlap1
    face_detailer_enabledfalse
    face_detailer_profilebalanced
    face_detailer_use_sam_maskfalse
    h3_upres_model_name
    h3_upres_precisionfp16
    h3_upres_devicecuda
    h3_upres_keep_models_residentfalse
    h3_upres_steps1
    h3_upres_denoise0.20
    h3_upres_samplersa_solver
    h3_upres_schedulersimple
    h3_upres_temporal_chunk85
    h3_upres_temporal_overlap17
    h3_upres_anchor_strength0.999
    h3_upres_tile_width864
    h3_upres_tile_height480
    h3_upres_overlap_width128
    h3_upres_overlap_height128
    h3_upres_fade_width32
    h3_upres_fade_height32
    h3_upres_min_tile_size256
    h3_upres_overlap_modeearlier
    h3_upres_overlap_blendlinear
    h3_upres_rtx_enabledfalse
    h3_upres_rtx_qualityULTRA
    h3_upres_pixel_groups1
    h3_upres_window_frames136
    h3_upres_window_overlap22
    h3_upres_pixel_methodrtx_vsr
    secondary_lora_enabledfalse
    secondary_lora_name
    secondary_lora_strength0.00
    motion_context_window_frames124
    h3_exact_profilertx_xx60_8_12gb_124
    h3_exact_chunk_rows2048
    h3_exact_precision_modePreserve native
    h3_exact_qkv_streamingAuto
    h3_exact_attention_memoryStandard
    h3_clipproj_profile4b_v3.1
    h3_clipproj_load_modedynamic
    h3_r40_seed_scout_enabledfalse
    h3_r40_candidate_count3
    h3_r40_seed_stride1000003
    h3_r40_preview_max_frames49
    h3_r40_sparse_enabledfalse
    h3_r40_sparse_video_budget0.30
    h3_r40_sparse_denser_edgestrue
    pdd_lora_name
    pdd_strength1.00
    h3_controlnet_enabledfalse
    h3_controlnet_name
    h3_controlnet_kindpose_dwpose
    h3_controlnet_strength1.00
    h3_controlnet_start_percent0.00
    h3_controlnet_end_percent1.00
    h3_controlnet_frame_scopetimeline_segment
    h3_controlnet_end_policystrict_match

    The IAMCCS_MiniMaxH3ShotPlanner (the Shotboard) has so many widgets that splitting the config from the planning is the obvious quality-of-life move. IAMCCS_ShotboardH3Settings is that split: it's the same settings surface as the Shotboard - same contracts, same option lists - but its only job is to package them into one cine_linx output that the Shotboard (or another consumer) can read. You can't get a cleaner separation of "configure once" from "plan each shot."

    How it works

    Rather than maintaining a second fragile widget schema, the node literally borrows the Shotboard's input definitions (IAMCCS_MiniMaxH3ShotPlanner.INPUT_TYPES()), groups them by category, and re-exposes them with display names like 08 · ADVANCED COMPATIBILITY · ltx round mode. That means every future option the Shotboard gains - samplers, installed LoRAs, new presets - appears here automatically. It also strips the control_after_generate auto-seed behavior, because this is a persisted configuration source, not a sampler; the Shotboard keeps the single seed control.

    Practically, you get the full set of Shotboard knobs here: duration_seconds, width/height (and the image-reference variants image_width/image_height with their resize method), guide_policy, default_force, promptrelay_epsilon, ltx_round_mode, and the rest of the H3 settings groups. You set them once, wire the cine_linx output into the Shotboard's cine_linx input, and the shot inherits them.

    Outputs

    A single output: cine_linx, carrying the settings payload under an iamccs_minimax_h3_settings schema with schema_version: 1. The node's policy strings make the priority explicit: minimax_h3_settings_source: IAMCCS_ShotboardH3Settings and minimax_h3_settings_priority: external_cine_linx_over_local_snapshot - i.e. when both an external settings CineLinX and the Shotboard's own widgets are present, the external config wins. That's the whole contract in two lines: this node is meant to be the authority, so don't fight it by also hand-editing the same fields in the Shotboard.

    Why you'd bother

    Two workflows make it worth it. First, presets: build two or three of these as saved config sources (a "hero quality" one, a "low VRAM draft" one) and switch between them by rewiring a single connection instead of scrolling fifty widgets. Second, consistency across many shots: if you always render the same canvas size, guide policy and round mode, locking them here removes a whole class of "one segment rendered at the wrong resolution" accidents.

    Ships with IAMCCS-nodes: ComfyUI Manager → search "IAMCCS", or cd ComfyUI/custom_nodes && git clone https://github.com/IAMCCS/IAMCCS-nodes.git, then restart. No extra models or dependencies beyond the pack.

    CategoryIAMCCS/MiniMax H3/Settings

    Inputs (139)

    NameTypeDefaultDescription
    duration_secondsFLOAT10.000.01–36000
    frame_rateINT2424–24
    guide_policyCOMBOevery_checked_row1 options: every_checked_row
    min_guide_gap_secondsFLOAT0.000–0
    max_guidesINT5050–50
    default_forceFLOAT1.001–1
    promptrelay_epsilonFLOAT0.00100.001–0.001
    ltx_round_modeCOMBOnone1 options: none
    widthINT960256–5760
    heightINT544256–5760
    image_widthINT960256–5760
    image_heightINT544256–5760
    image_resize_methodCOMBOcrop5 options: crop, pad, keep proportion, stretch,
    image_multiple_ofINT3232–32
    img_compressionINT00–100
    task_modeCOMBOauto_from_timeline11 options: auto_from_timeline, t2va, i2va, fl2va, ref2va, v2va_object_swap, +5
    audio_modeCOMBOh3_native_generated4 options: h3_native_generated, h3_ref2va_audio, h3_custom_audio_drive, external_audio_post
    prompt_mappingCOMBOglobal_plus_local3 options: global_plus_local, local_only, global_only
    performance_profileCOMBOlow_vram_balanced13 options: rtx_xx60_safe, rtx_xx70_balanced, rtx_xx80_quality, rtx_xx90_max, low_vram_draft, low_vram_balanced, +7
    text_encoder_deviceCOMBOgpu_auto4 options: gpu_auto, cpu_direct, auto, cpu_safe_12gb
    seedINT420–18446744073709550000
    seed_control_after_generate_compatSTRINGfixed
    seed_strideINT10–18446744073709550000
    stepsINT161–100
    sampler_nameCOMBOeuler44 options: res_multistep, euler, euler_cfg_pp, euler_ancestral, euler_ancestral_cfg_pp, heun, +38
    schedulerCOMBOsimple9 options: simple, sgm_uniform, karras, exponential, ddim_uniform, beta, +3
    denoiseFLOAT1.000–1
    shift_videoFLOAT12.000.01–100
    shift_audioFLOAT3.000.01–100
    turbo_modeCOMBOoff3 options: off, early_8_10, ckpt500_6_8
    turbo_lora_nameCOMBO1 options:
    turbo_strengthFLOAT1.000–4
    turbo_sampler_modeCOMBOaudio_fixed2 options: audio_fixed, res_multistep_stock
    reference_resize_policyCOMBOoff4 options: canvas_crop, canvas_pad, total_pixels, off
    reference_resize_megapixelsFLOAT0.500.1–2
    reference_resize_filterCOMBOarea4 options: area, bilinear, bicubic, nearest-exact
    accelerationCOMBOlow_vram_auto19 options: low_vram_auto, native, h3_sage, sol_low_vram, sol_adaptive_safe, sol_adaptive_balanced, +13
    ref_image_sizeCOMBOmatch2 options: match, max
    sol_conditioningCOMBOexact_kv_and_rows2 options: exact_kv_and_rows, exact_kv
    spectrum_profileCOMBOlow_vram5 options: low_vram, quality, aggressive, conservative_3060, conservative_quality
    vram_clean_before_decodeBOOLEANtrue
    rife_modeCOMBOoff3 options: off, rife_48fps, rife_60fps
    reference_role_1COMBOsubject_identity5 options: subject_identity, keyframe, composition, style, disabled
    reference_role_2COMBOsubject_identity5 options: subject_identity, keyframe, composition, style, disabled
    reference_role_3COMBOcomposition5 options: subject_identity, keyframe, composition, style, disabled
    reference_role_4COMBOstyle5 options: subject_identity, keyframe, composition, style, disabled
    reference_video_roleCOMBOoff5 options: off, motion_camera, temporal_structure, video_edit, continuation
    reference_audio_roleCOMBOoff5 options: off, voice_timbre, rhythm_timing, audio_reuse, sound_reference
    voice_reference_picture_indexINT00–4
    v2v_guide_modeCOMBOraw_only5 options: , raw_only, raw_pose, raw_depth, raw_depth_pose
    v2v_source_range_policyCOMBOtimeline_segment4 options: , timeline_segment, sequential_requested, repeat_from_offset
    v2v_source_offset_secondsFLOAT0.000–86400
    v2v_source_fitCOMBOcanvas_pad5 options: , native_adapt, canvas_pad, canvas_crop, stretch
    v2v_source_end_policyCOMBOhold_last_for_grid3 options: , hold_last_for_grid, error
    v2v_audio_pairingCOMBOpair_with_source_video4 options: , pair_with_source_video, standalone_reference, off
    flf_join_modeCOMBOh3_keyframe_cut2 options: h3_keyframe_cut, wan_overlap_blend
    flf_overlap_framesINT91–24
    flf_continuity_modeCOMBOstable_keyframes2 options: stable_keyframes, native_av_context
    flf_continuity_tail_framesCOMBO223 options: 22, 39, 56
    flf_continuity_audioBOOLEANtrue
    upscale_modeCOMBOoff8 options: off, rtx_final, h3_fast_latent_2pass, h3_pixel_refine, h3_latent_upres, ltx23, +2
    upscale_enabledBOOLEANfalse
    upscale_widthINT1920256–7680
    upscale_heightINT1080256–4320
    upscale_promptSTRING
    upscale_sageBOOLEANtrue
    upscale_seed_offsetINT100000–18446744073709550000
    wan_upscale_denoiseFLOAT0.200–1
    ltx_seam_safeBOOLEANtrue
    ltx_detailer_enabledBOOLEANfalse
    ltx_detailer_lora_nameCOMBO1 options:
    ltx_detailer_strengthFLOAT0.600–2
    ltx_4k_enabledBOOLEANfalse
    ltx_4k_qualityCOMBOULTRA4 options: ULTRA, HIGH, MEDIUM, LOW
    ltx_looper_temporal_tile_sizeINT8024–1000
    ltx_looper_temporal_overlapINT2416–80
    ltx_looper_guiding_strengthFLOAT1.000–1
    ltx_looper_overlap_strengthFLOAT0.500–1
    ltx_looper_cond_image_strengthFLOAT1.000–1
    ltx_looper_horizontal_tilesINT11–6
    ltx_looper_vertical_tilesINT11–6
    ltx_looper_spatial_overlapINT11–8
    face_detailer_enabledBOOLEANfalse
    face_detailer_profileCOMBObalanced4 options: balanced, small_faces, gentle, sam_face_mask
    face_detailer_use_sam_maskBOOLEANfalse
    h3_upres_model_nameCOMBOChoose an installed H3 3D latent upscaler. Auto uses an installed FP16 checkpoint first; no model is downloaded.
    h3_upres_precisionCOMBOfp163 options: fp16, bf16, fp32
    h3_upres_deviceCOMBOcuda2 options: cuda, cpu
    h3_upres_keep_models_residentBOOLEANfalse
    h3_upres_stepsINT11–20
    h3_upres_denoiseFLOAT0.200–1
    h3_upres_samplerCOMBOsa_solver44 options: euler, euler_cfg_pp, euler_ancestral, euler_ancestral_cfg_pp, heun, heunpp2, +38
    h3_upres_schedulerCOMBOsimple9 options: simple, sgm_uniform, karras, exponential, ddim_uniform, beta, +3
    h3_upres_temporal_chunkINT8517–1700
    h3_upres_temporal_overlapINT170–850
    h3_upres_anchor_strengthFLOAT0.9990–1
    h3_upres_tile_widthINT86432–4096
    h3_upres_tile_heightINT48032–4096
    h3_upres_overlap_widthINT1280–2048
    h3_upres_overlap_heightINT1280–2048
    h3_upres_fade_widthINT320–2048
    h3_upres_fade_heightINT320–2048
    h3_upres_min_tile_sizeINT2560–4096
    h3_upres_overlap_modeCOMBOearlier2 options: earlier, later
    h3_upres_overlap_blendCOMBOlinear4 options: linear, smoothstep, overwrite, midpoint
    h3_upres_rtx_enabledBOOLEANfalse
    h3_upres_rtx_qualityCOMBOULTRA4 options: ULTRA, HIGH, MEDIUM, LOW
    h3_upres_pixel_groupsINT11–16
    h3_upres_window_framesINT13634–510
    h3_upres_window_overlapINT220–170
    h3_upres_pixel_methodCOMBOrtx_vsr4 options: rtx_vsr, lanczos-ish bicubic, bilinear, nearest-exact
    secondary_lora_enabledBOOLEANfalse
    secondary_lora_nameCOMBO1 options:
    secondary_lora_strengthFLOAT0.00-2–2
    motion_context_window_framesINT12456–362Maximum native H3 sample window including the carried AV tail. 124 is safe for 8–12 GB VRAM; 209 or 362 reduces chunk count on larger VRAM classes.
    h3_exact_profileCOMBOrtx_xx60_8_12gb_124Editable hardware-class baseline: xx60 124f/5.17s, xx70 209f/8.71s, xx80 294f/12.25s, xx90 362f/15.08s. It never overrides the visible window, memory, ClipProj or sampling boxes.
    h3_exact_chunk_rowsINT2048256–655362048 is the conservative 8–12 GB value. Larger values can be faster but use more activation memory.
    h3_exact_precision_modeCOMBOPreserve nativePreserve native keeps INT8/W4A8 checkpoints in their released precision without an implicit conversion.
    h3_exact_qkv_streamingCOMBOAutoAuto preserves the current dense attention backend and adds bounded Q/K/V carriers only where compatible.
    h3_exact_attention_memoryCOMBOStandardLower VRAM performs extra exact attention work. It is a safety fallback, not an approximate cache.
    h3_clipproj_profileCOMBO4b_v3.14B v3.1 is the default lower-memory conditioning encoder. 8B is larger and heavier. Off uses the connected workflow fallback CLIP. This choice does not replace the MiniMax H3 denoiser model.
    h3_clipproj_load_modeCOMBOdynamicDynamic uses ComfyUI-managed offload. Streaming lowers the peak further at a speed cost.
    h3_r40_seed_scout_enabledBOOLEANfalseCandidate-scout workflows only. Samples low-resolution candidates before one selected take enters delivery; ordinary generation workflows ignore this field.
    h3_r40_candidate_countINT31–41 keeps normal cost; 2-4 create independent cacheable seed candidates. Use 3 for hero-shot scouting, not for every automatic LongVid chunk.
    h3_r40_seed_strideINT10000031–18446744073709550000Candidate N uses base seed + N × stride. 1,000,003 provides widely separated deterministic candidates without a hidden prompt or model override.
    h3_r40_preview_max_framesINT491–209Limits each candidate preview batch only; it never shortens or changes the generated AV latent.
    h3_r40_sparse_enabledBOOLEANfalseOptional current H3SparseAttention. Faster/lower VRAM can change motion, detail or prompt adherence; Off is the quality-safe default.
    h3_r40_sparse_video_budgetFLOAT0.300.05–1Fraction of video KV attention retained. 1.0 is dense-equivalent routing; 0.30 is faster but is not lossless.
    h3_r40_sparse_denser_edgesBOOLEANtrueAdds attention budget to the first and last sampling steps to protect layout, prompt adherence and final detail.
    pdd_lora_nameCOMBOSelect a native Kijai *_Acc-8Step*_comfy LoRA from models/loras and match FL2VA/Ref2VA to the loaded trunk. Legacy aptech pdd_acc files require their companion loader and are rejected here.
    pdd_strengthFLOAT1.000–2Keep 1.0. Native shape-changing PDD head banks require full trained strength; any different visible Queue-truth value fails clearly instead of being silently replaced.
    h3_controlnet_enabledBOOLEANfalseOFF preserves the standard generation path exactly. ON requires a preprocessed control-video CineLinX module and an installed H3 Fun ControlNet.
    h3_controlnet_nameCOMBOSelect the Kijai MiniMax H3 Fun ControlNet Union checkpoint from models/controlnet.
    h3_controlnet_kindCOMBOpose_dwposeDeclare the already-preprocessed input: DWPose, depth, Canny, HED, MLSD or inpaint. This does not run a hidden preprocessor.
    h3_controlnet_strengthFLOAT1.000–21.0 is the reference pose-control baseline. Lower values release structure; higher values can over-constrain identity and texture.
    h3_controlnet_start_percentFLOAT0.000–1Sampling interval start. 0.0 applies control from the first denoise step.
    h3_controlnet_end_percentFLOAT1.000–1Sampling interval end. 1.0 applies control throughout; earlier release can preserve more natural detail.
    h3_controlnet_frame_scopeCOMBOtimeline_segmentTimeline segment slices the full source by each Shotboard chunk start. Repeat each chunk restarts from source frame zero.
    h3_controlnet_end_policyCOMBOstrict_matchStrict match hard-fails before sampling if the source cannot cover the chunk. Hold last repeats the final control frame.

    Outputs (1)

    NameTypeDescription
    cine_linxIAMCCS_SUPERNODE_LINX